Tensorflow TF OD 2 API培训提前结束

这几天我一直在玩Tensorflow对象检测API 2（TFOD 2），我正在使用git头提交。我的目标是通过使用SensorFlow 2 model Zoo中现有的DL体系结构，为我的自定义数据集找到最合适的模型。我已经用下面的教程生成了我的TF记录，我一直在用我的笔记本电脑和Google Colab在GPU模式下对它进行训练

我发现这很神奇，虽然我尝试使用models/research/object\u detection/model\u main\u tf2.py来重现我的数据集的相同步骤，但不幸的是，训练脚本总是在开始迭代之前结束。它没有显示任何Python错误，并且像往常一样显示了一些警告。完整的输出在我的

我正在使用以下命令微调模型

 PIPELINE_CONFIG_PATH=models/ssd_resnet152_v1_fpn_640x640_coco17_tpu-8/pipeline.config; MODEL_DIR=training/; NUM_TRAIN_STEPS=10000; SAMPLE_1_OF_N_EVAL_EXAMPLES=1;

 python models/research/object_detection/model_main_tf2.py --model_dir=$MODEL_DIR --num_train_steps=$NUM_TRAIN_STEPS --sample_1_of_n_eval_examples=$SAMPLE_1_OF_N_EVAL_EXAMPLES --pipeline_config_path=$PIPELINE_CONFIG_PATH --alsologtostderr

这是我的pipeline.config文件

model {
  ssd {
    num_classes: 90
    image_resizer {
      fixed_shape_resizer {
        height: 640
        width: 640
      }
    }
    feature_extractor {
      type: "ssd_resnet152_v1_fpn_keras"
      depth_multiplier: 1.0
      min_depth: 16
      conv_hyperparams {
        regularizer {
          l2_regularizer {
            weight: 0.00039999998989515007
          }
        }
        initializer {
          truncated_normal_initializer {
            mean: 0.0
            stddev: 0.029999999329447746
          }
        }
        activation: RELU_6
        batch_norm {
          decay: 0.996999979019165
          scale: true
          epsilon: 0.0010000000474974513
        }
      }
      override_base_feature_extractor_hyperparams: true
      fpn {
        min_level: 3
        max_level: 7
      }
    }
    box_coder {
      faster_rcnn_box_coder {
        y_scale: 10.0
        x_scale: 10.0
        height_scale: 5.0
        width_scale: 5.0
      }
    }
    matcher {
      argmax_matcher {
        matched_threshold: 0.5
        unmatched_threshold: 0.5
        ignore_thresholds: false
        negatives_lower_than_unmatched: true
        force_match_for_each_row: true
        use_matmul_gather: true
      }
    }
    similarity_calculator {
      iou_similarity {
      }
    }
    box_predictor {
      weight_shared_convolutional_box_predictor {
        conv_hyperparams {
          regularizer {
            l2_regularizer {
              weight: 0.00039999998989515007
            }
          }
          initializer {
            random_normal_initializer {
              mean: 0.0
              stddev: 0.009999999776482582
            }
          }
          activation: RELU_6
          batch_norm {
            decay: 0.996999979019165
            scale: true
            epsilon: 0.0010000000474974513
          }
        }
        depth: 256
        num_layers_before_predictor: 4
        kernel_size: 3
        class_prediction_bias_init: -4.599999904632568
      }
    }
    anchor_generator {
      multiscale_anchor_generator {
        min_level: 3
        max_level: 7
        anchor_scale: 4.0
        aspect_ratios: 1.0
        aspect_ratios: 2.0
        aspect_ratios: 0.5
        scales_per_octave: 2
      }
    }
    post_processing {
      batch_non_max_suppression {
        score_threshold: 9.99999993922529e-09
        iou_threshold: 0.6000000238418579
        max_detections_per_class: 100
        max_total_detections: 100
        use_static_shapes: false
      }
      score_converter: SIGMOID
    }
    normalize_loss_by_num_matches: true
    loss {
      localization_loss {
        weighted_smooth_l1 {
        }
      }
      classification_loss {
        weighted_sigmoid_focal {
          gamma: 2.0
          alpha: 0.25
        }
      }
      classification_weight: 1.0
      localization_weight: 1.0
    }
    encode_background_as_zeros: true
    normalize_loc_loss_by_codesize: true
    inplace_batchnorm_update: true
    freeze_batchnorm: false
  }
}
train_config {
  batch_size: 8
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    random_crop_image {
      min_object_covered: 0.0
      min_aspect_ratio: 0.75
      max_aspect_ratio: 3.0
      min_area: 0.75
      max_area: 1.0
      overlap_thresh: 0.0
    }
  }
  sync_replicas: true
  optimizer {
    momentum_optimizer {
      learning_rate {
        cosine_decay_learning_rate {
          learning_rate_base: 0.03999999910593033
          total_steps: 25000
          warmup_learning_rate: 0.013333000242710114
          warmup_steps: 2000
        }
      }
      momentum_optimizer_value: 0.8999999761581421
    }
    use_moving_average: false
  }
  fine_tune_checkpoint_version: V2
  fine_tune_checkpoint: "models/ssd_resnet152_v1_fpn_640x640_coco17_tpu-8/checkpoint/ckpt-0"
  num_steps: 25000
  startup_delay_steps: 0.0
  replicas_to_aggregate: 8
  max_number_of_boxes: 100
  unpad_groundtruth_tensors: false
  fine_tune_checkpoint_type: "classification"
  use_bfloat16: true
}
train_input_reader {
  label_map_path: "datasets/UrbanTracker/urban_tracker_label_map.pbtxt"
  tf_record_input_reader {
    input_path: "datasets/UrbanTracker/urban_tracker_train.record"
  }
}
eval_config {
  metrics_set: "coco_detection_metrics"
  use_moving_averages: false
}
eval_input_reader {
  label_map_path: "datasets/UrbanTracker/urban_tracker_label_map.pbtxt"
  shuffle: false
  num_epochs: 1
  tf_record_input_reader {
    input_path: "datasets/UrbanTracker/urban_tracker_test.record"
  }
}

这就是我的模型目录的样子

.
├── datasets
│   ├── raccoon
│   │   ├── raccoon_label_map.pbtxt
│   │   ├── raccoon_test.record
│   │   └── raccoon_train.record
│   ├── readme.md
│   └── UrbanTracker
│       ├── labels_urbantracker.txt
│       ├── urban_tracker_label_map.pbtxt
│       ├── urban_tracker_test.record
│       └── urban_tracker_train.record
├── __main__.py
├── models
│   ├── AUTHORS
│   ├── efficientdet_d1_coco17_tpu-32
│   │   ├── checkpoint
│   │   │   ├── checkpoint
│   │   │   ├── ckpt-0.data-00000-of-00001
│   │   │   └── ckpt-0.index
│   │   ├── pipeline.config
│   │   ├── saved_model
│   │   │   ├── assets
│   │   │   ├── saved_model.pb
│   │   │   └── variables
│   │   │       ├── variables.data-00000-of-00001
│   │   │       └── variables.index
│   ├── faster_rcnn_resnet101_v1_640x640_coco17_tpu-8
│   │   ├── checkpoint
│   │   │   ├── checkpoint
│   │   │   ├── ckpt-0.data-00000-of-00001
│   │   │   └── ckpt-0.index
│   │   ├── pipeline.config
│   │   ├── saved_model
│   │   │   ├── saved_model.pb
│   │   │   └── variables
│   │   │       ├── variables.data-00000-of-00001
│   │   │       └── variables.index
│   └── ssd_resnet152_v1_fpn_640x640_coco17_tpu-8
│       ├── checkpoint
│       │   ├── checkpoint
│       │   ├── ckpt-0.data-00000-of-00001
│       │   └── ckpt-0.index
│       ├── pipeline.config
│       ├── saved_model
│       │   ├── assets
│       │   ├── saved_model.pb
│       │   └── variables
│       │       ├── variables.data-00000-of-00001
│       │       └── variables.index
├── tools
│   ├── parse_polytrack.py
│   ├── polytrack_csv_to_tfrecord.py
│   ├── raccoon_labels_test.csv
│   ├── raccoon_labels_train.csv
│   ├── split_dataset.py
│   ├── urban_tracker_test.csv
│   └── urban_tracker_train.csv

我已使用TFV1和v2 API将数据集转换为TFRecord。此外，我一直在使用不同的训练参数，但运气不佳。为了检查我的数据集，如果我生成了错误的数据集，我尝试使用另一个数据集，基本数据集，但得到了相同的结果

---

感谢您的关注。

已解决：对于efficientdet\u d1\u CoCoCo17\u tpu-32等型号，只需在管道中更改。将参数从

微调检查点类型：“分类”

配置为

微调检查点类型：“检测”

，检查

已解决：对于诸如efficientdet\u d1\u CoCoCo17\u tpu-32之类的模型，只需在管道中进行更改。将参数从

微调检查点类型：“分类”

配置为

微调检查点类型：“检测”

，请选中